{"id":"https://openalex.org/W2460742184","doi":"https://doi.org/10.1109/icassp.2017.7952154","title":"Permutation invariant training of deep models for speaker-independent multi-talker speech separation","display_name":"Permutation invariant training of deep models for speaker-independent multi-talker speech separation","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2460742184","doi":"https://doi.org/10.1109/icassp.2017.7952154","mag":"2460742184"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006420917","display_name":"Morten Kolb\u00e6k","orcid":"https://orcid.org/0000-0002-2561-4960"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Morten Kolbaek","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":879,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7552098631858826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6796722412109375},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.6385685205459595},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6265685558319092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5599410533905029},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5581746101379395},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5496063828468323},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5230439901351929},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4791554808616638},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4738774001598358},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.45572227239608765},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45180028676986694},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4351913630962372},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4218434691429138},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28875553607940674},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13353830575942993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7552098631858826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6796722412109375},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.6385685205459595},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6265685558319092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5599410533905029},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5581746101379395},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5496063828468323},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5230439901351929},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4791554808616638},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4738774001598358},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.45572227239608765},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45180028676986694},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4351913630962372},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4218434691429138},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28875553607940674},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13353830575942993},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2017.7952154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/09649e0f-6ff5-48a7-aea4-5fc9c815f970","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/09649e0f-6ff5-48a7-aea4-5fc9c815f970","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yu , D , Kolb\u00e6k , M , Tan , Z-H & Jensen , J 2017 , Permutation invariant training of deep models for speaker-independent multi-talker speech separation . in International Conference on Acoustics, Speech and Signal Processing (ICASSP) . IEEE , pp. 241 - 245 , The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing , New Orleans , United States , 05/03/2017 . https://doi.org/10.1109/ICASSP.2017.7952154","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320315072","display_name":"Mitsubishi Electric Research Laboratories","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W80444264","https://openalex.org/W185399533","https://openalex.org/W217970951","https://openalex.org/W1528056001","https://openalex.org/W1550027367","https://openalex.org/W1748744376","https://openalex.org/W1790748249","https://openalex.org/W1897240248","https://openalex.org/W1991139021","https://openalex.org/W2060822897","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2116879786","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2144763279","https://openalex.org/W2147174722","https://openalex.org/W2147768505","https://openalex.org/W2149648698","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2221409856","https://openalex.org/W2315268655","https://openalex.org/W2394932179","https://openalex.org/W2962715207","https://openalex.org/W3124794156","https://openalex.org/W6603255414","https://openalex.org/W6607486085","https://openalex.org/W6608710415","https://openalex.org/W6682181234"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W34555840"],"abstract_inverted_index":{"We":[0,66],"propose":[1],"a":[2],"novel":[3,38],"deep":[4,33,59],"learning":[5,60],"training":[6,11],"criterion,":[7],"named":[8],"permutation":[9,52],"invariant":[10],"(PIT),":[12],"for":[13,63],"speaker":[14],"independent":[15],"multi-talker":[16],"speech":[17,64],"separation,":[18],"commonly":[19],"known":[20],"as":[21],"the":[22,27,32,41,49,70,129],"cocktail-party":[23,130],"problem.":[24,131],"Different":[25],"from":[26],"multi-class":[28],"regression":[29],"technique":[30],"and":[31,72,77,93,95,101,109,114],"clustering":[34],"(DPCL)":[35],"technique,":[36],"our":[37],"approach":[39],"minimizes":[40],"separation":[42,75],"error":[43],"directly.":[44],"This":[45],"strategy":[46],"effectively":[47],"solves":[48],"long-lasting":[50],"label":[51],"problem,":[53],"that":[54,79],"has":[55],"prevented":[56],"progress":[57],"on":[58,69],"based":[61],"techniques":[62],"separation.":[65],"evaluated":[67],"PIT":[68,104,125],"WSJ0":[71],"Danish":[73],"mixed-speech":[74],"tasks":[76],"found":[78],"it":[80],"compares":[81],"favorably":[82],"to":[83,107],"non-negative":[84],"matrix":[85],"factorization":[86],"(NMF),":[87],"computational":[88],"auditory":[89],"scene":[90],"analysis":[91],"(CASA),":[92],"DPCL":[94],"generalizes":[96],"well":[97],"over":[98],"unseen":[99],"speakers":[100],"languages.":[102],"Since":[103],"is":[105],"simple":[106],"implement":[108],"can":[110,126],"be":[111],"easily":[112],"integrated":[113],"combined":[115],"with":[116],"other":[117],"advanced":[118],"techniques,":[119],"we":[120],"believe":[121],"improvements":[122],"built":[123],"upon":[124],"eventually":[127],"solve":[128]},"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":67},{"year":2024,"cited_by_count":82},{"year":2023,"cited_by_count":99},{"year":2022,"cited_by_count":112},{"year":2021,"cited_by_count":153},{"year":2020,"cited_by_count":163},{"year":2019,"cited_by_count":107},{"year":2018,"cited_by_count":52},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}